When Does Confidence-Based Cascade Deferral Suffice? Wittawat Jitkrittum Neha Gupta Aditya Krishna Menon Harikrishna Narasimhan Ankit Singh Rawat Sanjiv Kumar Google Research, New York

Neural Information Processing Systems 

One simple deferral rule employs the confidence of the current classifier, e.g., based on the maximum predicted softmax probability.